top of page

MLP@P- Machine Learning Physics @ Plateau

Informal meetings on statistical physics & machine learning

Organized by:

Sergio Chibbaro (LISN)

Cyril Furtlehner (LISN)

Valentina Ros (LPTMS)

Pierfrancesco Urbani (IPhT)

To subscribe to the mailing list, write to valentina.ros@cnrs.fr

Mini-workshop on Class Imbalance

When: Friday, November 15 2024,  all day

Where: LPTMS, petit Amphi (1° étage)

Emanuele Francazi – A theoretical analysis of the learning dynamics under class imbalance 

Stefano Sarao-Mannelli – Bias-inducing geometries: exactly solvable data model with fairness implications

Mauro Pastore – Restoring balance: principled under/oversampling of data for optimal classification

Francesco Saverio Pezzicoli – Anomaly-Detection Class Imbalance in Exactly Solvable Models

Seminar by Gabriele Sicuro, University of Bologna

When: Friday, October 4 2024, at 11:00am

Where: LISN, bat 660 salle 2014 (2° étage)

Heavy-tailed covariates in high dimensions

 

Machine learning theoretical models very often assume a dataset obtained from a Gaussian distribution, or from a Gaussian mixture. The possible limitations of such a Gaussian assumption have been recently object of investigation, and theoretically characterization, leading to a number of "Gaussian universality" results. In this talk I will present an analytical treatment of the performance in high dimensions of simple architectures on heavy-tailed distributed datasets, showing that even simple generalized linear models exhibit a striking dependence on non-Gaussian features in both classification and regression tasks.

SUBSCRIBE FOR ALL DigiSF UPDATES

bottom of page